Merge pull request #384 from capitalone/develop

Release v0.16.3

datacompy/__init__.py

@@ -18,7 +18,7 @@
 Then extended to carry that functionality over to Spark Dataframes.
 """
 
-__version__ = "0.16.2"
+__version__ = "0.16.3"
 
 import platform
 from warnings import warn

datacompy/snowflake.py

@@ -163,7 +163,7 @@ def df1(self, df1: tuple[Union[str, "sp.DataFrame"], str | None]) -> None:
             if len(table_name) != 3:
                 errmsg = f"{df} is not a valid table name. Be sure to include the target db and schema."
                 raise ValueError(errmsg)
-            self.df1_name = df_name.upper() if df_name else table_name[2]
+            self.df1_name = df_name.upper() if df_name else "__".join(table_name)
             self._df1 = self.session.table(df)
         else:
             self._df1 = df
@@ -184,7 +184,7 @@ def df2(self, df2: tuple[Union[str, "sp.DataFrame"], str | None]) -> None:
             if len(table_name) != 3:
                 errmsg = f"{df} is not a valid table name. Be sure to include the target db and schema."
                 raise ValueError(errmsg)
-            self.df2_name = df_name.upper() if df_name else table_name[2]
+            self.df2_name = df_name.upper() if df_name else "__".join(table_name)
             self._df2 = self.session.table(df)
         else:
             self._df2 = df

docs/source/snowflake_usage.rst

@@ -7,6 +7,9 @@ For ``SnowflakeCompare``
 - Joining is done using ``EQUAL_NULL`` which is the equality test that is safe for null values.
 - Compares ``snowflake.snowpark.DataFrame``, which can be provided as either raw Snowflake dataframes
   or as the names of full names of valid snowflake tables, which we will process into Snowpark dataframes.
+- Note that if Snowflake tables are provided, that dataframe names will default to the full name of their
+respective Snowflake tables. This can be overriden by setting the ``df1_name`` and ``df2_name`` arguments
+when creating the Compare object.
 
 
 SnowflakeCompare setup
@@ -57,6 +60,8 @@ Provide Snowpark dataframes
         session,
         df_1,
         df_2,
+        #df1_name='original', # optional param for naming df1
+        #df2_name='new' # optional param for naming df2
         join_columns=['acct_id'],
         rel_tol=1e-03,
         abs_tol=1e-04,
@@ -80,6 +85,8 @@ Given the dataframes from the prior examples...
         session,
         f"{db}.{schema}.toy_table_1",
         f"{db}.{schema}.toy_table_2",
+        #df1_name='original', # optional param for naming df1
+        #df2_name='new' # optional param for naming df2
         join_columns=['acct_id'],
         rel_tol=1e-03,
         abs_tol=1e-04,

pyproject.toml

@@ -13,7 +13,7 @@ maintainers = [
   { name="Raymond Haffar", email="[email protected]" },
 ]
 license = {text = "Apache Software License"}
-dependencies = ["pandas<=2.2.3,>=0.25.0", "numpy<=2.2.0,>=1.22.0", "ordered-set<=4.1.0,>=4.0.2", "polars[pandas]<=1.17.1,>=0.20.4"]
+dependencies = ["pandas<=2.2.3,>=0.25.0", "numpy<=2.2.3,>=1.22.0", "ordered-set<=4.1.0,>=4.0.2", "polars[pandas]<=1.22.0,>=0.20.4"]
 requires-python = ">=3.10.0"
 classifiers = [
     "Intended Audience :: Developers",
@@ -55,7 +55,7 @@ version = {attr = "datacompy.__version__"}
 python-tag = "py3"
 
 [project.optional-dependencies]
-fugue = ["fugue[duckdb,dask,ray]<=0.9.1,>=0.8.7"]
+fugue = ["fugue[dask,duckdb,ray]<=0.9.1,>=0.8.7"]
 spark = ["pyspark[connect]>=3.1.1; python_version < \"3.11\"", "pyspark[connect]>=3.4; python_version >= \"3.11\""]
 snowflake = ["snowflake-connector-python", "snowflake-snowpark-python"]
 docs = ["sphinx", "furo", "myst-parser"]

tests/test_snowflake.py

@@ -356,6 +356,31 @@ def test_compare_table_setter_bad(snowpark_session):
         )
 
 
+@mock.patch(
+    "datacompy.snowflake.SnowflakeCompare._validate_dataframe", new=mock.MagicMock()
+)
+@mock.patch("datacompy.snowflake.SnowflakeCompare._compare", new=mock.MagicMock())
+def test_compare_table_unique_names(snowpark_session):
+    # Assert that two tables with the same name but from a different DB/Schema have unique names
+    # Same schema/name, different DB
+    compare = SnowflakeCompare(
+        snowpark_session,
+        "test_db1.test_schema.test_name",
+        "test_db2.test_schema.test_name",
+        ["A"],
+    )
+    assert compare.df1_name != compare.df2_name
+
+    # Same db/name, different schema
+    compare = SnowflakeCompare(
+        snowpark_session,
+        "test_db.test_schema1.test_name",
+        "test_db.test_schema2.test_name",
+        ["A"],
+    )
+    assert compare.df1_name != compare.df2_name
+
+
 def test_compare_table_setter_good(snowpark_session):
     data = """ACCT_ID,DOLLAR_AMT,NAME,FLOAT_FLD,DATE_FLD
     10000001234,123.4,George Michael Bluth,14530.155,